Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models versus Fine-Tuned Vision Transformers in Image-Based Security Applications.

@article{trad-2025-evaluating, author = {Fouad Trad and Ali Chehab}, title = {{Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models versus Fine-Tuned Vision Transformers in Image-Based Security Applications}}, journal = {ACM Transactions on Intelligent Systems and Technology (TIST)}, volume = {16}, number = {4}, pages = {89:1--89:22}, year = {2025}, url = {https://doi.org/10.1145/3735648}, doi = {https://doi.org/10.1145/3735648} }